IDK Depth of Field

# IDK Depth Of Field Camera V2

## About

Adds realistic shallow depth of field, cinematic bokeh, and background blur. Perfect for portrait photography style and dramatic compositions.

PT-BR: LoRA focada no conceito 'Depth Of Field Camera' para modelos SDXL baseados em Illustrious. Reforca a geracao de depth of field.

## Trigger words

### Primary triggers

```

depth of field

```

### Supporting tags

Frequent thematic tags from the training set - combine them with the primary triggers to steer the concept:

```

blurry, blurry background, realistic, photo (medium), photorealistic, long hair, lips, makeup, thighs, brown hair, nose, lipstick, ass, black hair

```

Also works with the V1 triggers: shallow depth of field, heavily blurred background, heavy bokeh, cinematic bokeh, depth of field

## Example prompts

```

masterpiece, best quality, absurdres, shallow depth of field, beautiful woman in focus with creamy bokeh background, romantic portrait, soft foreground blur, <lora:IDK_depth-of-field-camera_V2:0.9>

```

```

masterpiece, best quality, absurdres, shallow depth of field, beautiful woman in focus with creamy bokeh background, intimate nude study, sharp eyes, <lora:IDK_depth-of-field-camera_V2:0.9>

```

## Preview generation settings

| Setting | Value |

| --- | --- |

| Checkpoint | IDN_Illustrious_V10_T |

| Size | 1280x720 + hires 1.5x RealESRGAN 4x+) = 1920x1080 |

| Sampler | Euler a |

| Steps | 28 (+14 hires) |

| CFG scale | 5.5 |

| Denoising strength | 0.4 |

| Seeds | 1000-1009 |

Negative prompt: worst quality, low quality, bad anatomy, bad hands, extra digits, fewer digits, missing fingers, jpeg artifacts, signature, watermark, username, blurry, lowres, bad proportions, deformed, mutated

## Recommended weight

Use 0.8-1.1. This file is a V1+V2 merge (rank concatenation), which slightly dilutes each source - it tolerates and often benefits from weights a bit above 1.0.

## Changelog V2

- New, larger and more diverse training dataset.

- 1080p preview images.

- Merged with the V1 LoRA, so V1 behavior is preserved.

Base model: Illustrious SDXL IDN_Illustrious_V10_T)

Training pipeline: [IDK-Trainer](https://github.com/NOTcisLol/IDK-Trainer)

File: IDK_depth-of-field-camera_V2.safetensors